iterative-retrieval

Refine codebase context for subagents through an iterative retrieval loop.

2|Updated Mar 3, 2026

Search Tags:#codebase #evaluation #multi-agent #context-management #iterative-retrieval #retrieval-pattern

Ready to run

npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill iterative-retrieval-momodaviluke

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iterative-retrieval
Source: https://github.com/MomoDaviluke/star-citizen-promotion/tree/main/.agents/skills/ecc/iterative-retrieval
Command: npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill iterative-retrieval-momodaviluke

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents in multi-agent workflows often start with incomplete context and must discover which files or patterns are relevant. The Iterative Retrieval Pattern solves this by progressively refining the information fed to subagents, reducing context size while increasing usefulness.

Core Features & Use Cases

Four-phase loop: Dispatch, Evaluate, Refine, Loop, enabling controlled, incremental discovery.
Relevance scoring and gap identification to guide subsequent searches.
Flexible adaptations for codebase exploration, task-specific retrieval, and context-driven agent orchestration.
Examples include gathering context for bug fixes, feature implementations, or codebase audits where context unfolds across cycles.

Quick Start

Initiate the Iterative Retrieval Pattern to progressively refine codebase context across up to three cycles.

Frequently Asked Questions about iterative-retrieval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I provide relevant codebase context to subagents when starting with incomplete information?▼

To provide relevant codebase context to subagents, use an iterative retrieval loop that progressively discovers and refines files through relevance scoring and dynamic query refinement across up to three cycles.

What is the best way to handle missing-context failures in multi-agent workflows?▼

Handling missing-context failures in multi-agent workflows requires a four-phase loop: Dispatch, Evaluate, Refine, and Loop, which identifies context gaps and dynamically refines subsequent searches to resolve missing information.

How does iterative retrieval reduce context size while increasing usefulness for large codebases?▼

Iterative retrieval reduces context size for large codebases by applying relevance scoring and gap identification after each dispatch, ensuring only high-relevance files are passed forward to subagents.

Can I use iterative retrieval for codebase exploration tasks like bug fixes and feature implementations?▼

Yes, iterative retrieval supports codebase exploration for bug fixes, feature implementations, and codebase audits where relevant file patterns and context unfold progressively across multiple search cycles.

Does the iterative retrieval pattern support file-pattern search within a multi-agent context management workflow?▼

The iterative retrieval pattern integrates file-pattern search directly into its multi-agent context management workflow, using dynamic query refinement to locate and score relevant files for subagent dispatch.

What are the limitations of using a three-cycle maximum iterative retrieval loop for context discovery?▼

The iterative retrieval loop limits context discovery to a maximum of three cycles, meaning highly complex or deeply nested codebases may require manual intervention if relevant context is not identified within those iterations.